© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 12058
    Prev
    Next
    INDEX
    Explanations

    **Lessons**

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a comparison of quantity or extent, particularly involving the term "less."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.71
    ãĤ±
    -0.69
    DATA
    -0.64
     QC
    -0.63
    GB
    -0.62
    TAG
    -0.61
    ORN
    -0.60
    GL
    -0.60
    Ò
    -0.59
    ç·
    -0.59
    POSITIVE LOGITS
     Than
    0.89
     than
    0.86
    ened
    0.81
    ening
    0.80
    erton
    0.78
    vasive
    0.73
    ons
    0.70
    ners
    0.69
    ainers
    0.67
    than
    0.67
    Activations Density 0.019%

    No Known Activations